Gmf Robotics Corporation

Bruce E Coldren

Kenneth W Krause

H Dean McGee

A method and system for automatically determining the position and orientation of an object by utilizing as few as a single digital image generated by as few as a single camera without the use of a structured light. The digital image contains at least three non-colinear geometric features of the object. The three features may be either coplanar or non-coplanar. The features or targets are viewed such that perspective information is present in the digital image. In a single camera system the geometric features are points, and in a multi-camera system, the features are typically combinations of points and lines. The location of the features are determined and processed within a programmed computer together with reference data and camera calibration data to provide at least three non-parallel 3-D lines. The 3-D lines are utilized by an iterative algorithm to obtain data relating to the position and orientation of the object in 3-D space. The resultant data is subsequently utilized to calculate an offset of the object from the camera. The offset is then transformed into the coordinate system or frame of a peripheral device such as a robot, programmable controller, numerically controlled machine, etc. Finally, the programmed computer transfers the transformed offset to the peripheral device which utilizes the transformed offset to modify its preprogrammed path.

Method and system for automatically determining the position and

A method and system are provided for automatically locating an object at a vision station by performing an edge-detecting algorithm on at least a portion of the gray-scale digitized image of the object. Preferably, the algorithm comprises an implementation of the Hough transform which includes the iterative application of a direction-sensitive, edge-detecting convolution to the digital image. Each convolution is applied with a different convolution mask or filter, each of which is calculated to give maximum response to an edge of the object in a different direction. The method and system have the ability to extract edges from low contrast images. Also, preferably, a systolic array processor applies the convolutions. The implementation of the Hough transform also includes the steps of shifting the resulting edge-enhanced images by certain amounts in the horizontal and vertical directions, summing the shifted images together into an accumulator buffer to obtain an accumulator image and detecting the maximum response in the accumulator image which corresponds to the location of an edge. If the object to be found is permitted to rotate, at least one other feature, such as another edge, must be located in order to specify the location and orientation of the object. The location of the object when correlated with the nominal position of the object at the vision station provides the position and attitude of the object. The resultant data may be subsequently transformed into the coordinate frame of a peripheral device, such as a robot, programmable controller, numerical controlled machine, etc. for subsequent use by a controller of the peripheral device.

Growing community of inventors

Troy, MI, United States of America

Bruce E Coldren